© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 23308
    Prev
    Next
    INDEX
    Explanations

    hurt or injured

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_56_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Pape
    0.38
    ਕੇ
    0.38
    KET
    0.37
     IDX
    0.36
     dal
    0.36
     obliv
    0.35
    Skull
    0.35
    异
    0.35
     PAN
    0.34
     irregularities
    0.34
    POSITIVE LOGITS
     hurt
    1.80
     injured
    1.64
     Hurt
    1.56
    hurt
    1.48
     sp
    1.28
    injured
    1.27
     hurting
    1.26
     Inj
    1.25
     injure
    1.23
     hurts
    1.22
    Activations Density 0.040%

    No Known Activations